Data-driven computational homogenization using neural networks: FE2-NN application on damaged masonryData-driven computational homogenization using neural networks: FE2-NN application on damaged masonry Peer-Reviewed Journal Publication Δημοσίευση σε Περιοδικό με Κριτές 2023-01-312021enThe work has been partially supported by a Greek Diaspora Fellowship granted to the first author, supported by Stavros S. Niarchos Foundation and Fulbright Programme.Fusion of data mining and computational mechanics is a modern approach for the exploitation of available data within rigorous modeling. First steps in this direction have been focused on the usage of neural networks and other soft computing tools as metamodeling tools. This framework seems suitable for numerical homogenization techniques realized within the so-called FE2 environment, where the lower-level analysis of a detailed representative volume element is replaced by a prediction based on a previously prepared database. Numerically prepared data are used here, although the method can be used with experimental data as well. In this case, the need for a constitutive description of the fine scale is bypassed. Extraction of material properties from the database, required by the upper-level finite element analysis, is based on backpropagation artificial neural networks. The method is applicable to monuments and masonry structural systems. We investigate this approach here for the analysis of masonry structures with elastoplastic behavior. Results indicate a satisfactory comparison with published research.http://creativecommons.org/licenses/by/4.0/ACM Journal on Computing and Cultural Heritage141 Drosopoulos Georgios Δροσοπουλος Γεωργιος Stavroulakis Georgios Σταυρουλακης Γεωργιος Association for Computing Machinery (ACM) Numerical homogenization Masonry structures Data-driven multiscale analysis Neural network metamodels